INDEX

Explanations

Latin words and their meanings

oai_token-act-pair · gpt-3.5-turbo

references to Latin and English words

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

psey

-0.92

DERR

-0.79

roxy

-0.77

etheus

-0.71

ithing

-0.70

 Skydragon

-0.69

©¶æ¥µ

-0.69

ersen

-0.68

ONSORED

-0.68

 Democr

-0.65

POSITIVE LOGITS

sworth

1.07

mith

1.05

matical

0.92

ifier

0.88

 meanings

0.85

word

0.82

 Meaning

0.81

paces

0.81

words

0.81

ifiers

0.79

Activations Density 0.032%

Latin words and their meanings

references to Latin and English words

No Comments

No Known Activations